The Data Science & Machine Learning Developer Certification program provides a comprehensive set of knowledge and skills in data science, machine learning, and deep learning.  This immersive training curriculum covers all the key technologies, techniques, principles and practices you need to play a key role on your data science development team, and to distinguish yourself professionally.

Beginning with foundational principles and concepts used in data science and machine learning, this program moves progressively and rapidly to cover the foundational components at the core of machine learning. The program builds on the foundations and quickly moves into deep learning, along the way teaching you via lectures and interactive online labs.  The training uses open-source tools — along with your developing judgment and intuition — to address actual business needs and real-world challenges.

This program also covers the significant development of deep learning methods that enable state-of-the-art performance for many tasks, including image classification, time series (such as audio) classification and natural language processing. In this program, delegates gain hands-on deep learning experience.

Delegates will learn by hands-on labs working tools including Python, Scikit-Learn, Keras, and Tensorflow.

Target Audience/Who Should Enroll for Data Science & Machine Learning Developer Certification

• Developers aspiring to be a data scientist or machine learning engineer
• Developers seeking to understand machine and deep learning to be more valuable in their role interfacing with data scientists
• Analytics managers who are leading a team of analysts
• Business analysts who want to understand data science techniques
• Information architects who need expertise in machine learning algorithms
• Analytics professionals who work in machine learning or artificial intelligence
• Graduates looking to build a career in data science and machine learning

Prerequisites for Data Science & Machine Learning

• Exposure to coding (Python is helpful but not an absolute must)
• Exposure to math or, at the very least, no aversion (linear algebra helpful but not required)

What You Will Learn (Upon completion of this program, you will be able to):

• Develop solutions to real-world machine learning problems
• Explain and discuss the essential concepts of machine learning and in particular deep learning
• Implement supervised and unsupervised learning models for tasks such as forecasting, predicting and outlier detection
• Apply and use advanced machine learning applications, including recommendation systems and natural language processing
• Evaluate and apply deep learning concepts and software applications
• Identify, source and prepare raw data for analysis and modelling
• Work with open source tools such as Python, Scikit-learn, Keras and Tensorflow

Modules and Components in Curriculum

Introduction to Machine Learning

• What is machine learning?
• Installation and update of tools
• Machine learning algorithms

Exploring and Using Data Sets

• Defining and pre-processing datasets
• Prepare data for machine learning algorithms
• Supervised vs. unsupervised learning

Review of Machine Learning Algorithms

• Classification, linear regression and logistic regression
• Random forests, clustering
• Decision trees

Machine Learning with Scikit

• Recognize where to use ML
• Select best techniques
• Manipulate data with Pandas
• Visualize data with Matplotlib
• Solve regressions & classifications
• Evaluate model performance
• Serve models with Flask & Heroku

Deep Learning with Keras and TensorFlow

• Discover why TensorFlow is popular
• Advantages of Keras API for TensorFlow
• Understand DL fundamentals
• Build Fully Connected Neural Networks
• Train Convolutional Neural Networks
• Design Recurrent Neural Networks
• Create Embeddings
• Leverage Dropout & Batch Norm
• Use GPUs to train faster
• Visualize learning with TensorBoard

Deeper Understanding of Tensorflow

• Turn Keras models into Estimators
• Debug models with Eager Execution
• Scale to large dataset with Data API
• Learn about Core API
• Deploy models using cloud services

Building a Machine Learning Pipeline

(Important note: this module requires familiarity with one of the clouds, i.e. AWS)

• Overview of The Tools and Services
• Best Practices of Building an ML Pipeline
• Understanding Classifier Selection
• Insights Into Hyperparameter Optimization
• Understanding of Data Preprocessing
• Goals of Preprocessing
  • Handling missing data
  • Data Transformation
  • Outliers
  • Categorical Data
• Feature Extraction
  • Co-relation of Features
  • Dimensionality Reduction PCA
• Model Training
  • Linear Regression
  • Decision Tree
  • Ensemble Models
  • Feedback and Deployment

Applications that delegates will build

• Predict the price of a house
• Detect language of a text
• Recognize an object in an image
• Classify the sentiment in a sentence
• Forecast future energy consumption
• Deploy an API that predicts phone location from wifi signal

• Starweaver On-Air courses